Learning to Play General Video-Games via an Object Embedding Network
This addresses the inefficiency and unnaturalness of pixel-based learning for video-game AI, offering a more human-like approach, though it appears incremental as it builds on existing DRL methods.
The paper tackles the problem of deep reinforcement learning agents relying on pixel-based video data for general video-game AI, which is inefficient and unlike human play, by proposing an object embedding network that allows agents to learn directly from object information. The result is an agent that achieves performance comparable to state-of-the-art approaches on games from the GVG-AI Competition.
Deep reinforcement learning (DRL) has proven to be an effective tool for creating general video-game AI. However most current DRL video-game agents learn end-to-end from the video-output of the game, which is superfluous for many applications and creates a number of additional problems. More importantly, directly working on pixel-based raw video data is substantially distinct from what a human player does.In this paper, we present a novel method which enables DRL agents to learn directly from object information. This is obtained via use of an object embedding network (OEN) that compresses a set of object feature vectors of different lengths into a single fixed-length unified feature vector representing the current game-state and fulfills the DRL simultaneously. We evaluate our OEN-based DRL agent by comparing to several state-of-the-art approaches on a selection of games from the GVG-AI Competition. Experimental results suggest that our object-based DRL agent yields performance comparable to that of those approaches used in our comparative study.